论文标题
与神经增量ASR，MT和TTS的同时语音到语音翻译系统
Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS
论文作者
论文摘要
本文介绍了新开发的同时神经语音到语音翻译系统及其评估。该系统由三个用于自动语音识别（ASR），机器翻译（MT）和文本到语音综合（TTS）的全部信息神经处理模块组成。我们调查了其在系统的耳朵范围内的总体延迟，并讲话延迟以及模块级的性能。
This paper presents a newly developed, simultaneous neural speech-to-speech translation system and its evaluation. The system consists of three fully-incremental neural processing modules for automatic speech recognition (ASR), machine translation (MT), and text-to-speech synthesis (TTS). We investigated its overall latency in the system's Ear-Voice Span and speaking latency along with module-level performance.
